Decentralized Fairness Aware Multi Task Federated Learning for VR Network

2025-12-02

AI Summary

To address the low caching efficiency and unfair user experience arising from concurrent ultra-low latency, high-fidelity transmission requirements, and statistical heterogeneity among users and base stations in wireless VR networks, this paper proposes a decentralized multi-task fair federated learning caching framework. The framework enables collaborative training of personalized field-of-view (FoV) prediction models at base stations to achieve accurate content prefetching. It innovatively integrates multi-task learning with fairness constraints to jointly optimize inter-user QoE fairness and robustness to statistical heterogeneity. A PAC-learnable generalization error bound is theoretically established via Rademacher complexity analysis. Evaluated on real-world VR head-motion traces, the framework achieves a 23.6% improvement in cache hit ratio, a 31.4% reduction in end-to-end latency, and a 47.2% decrease in user QoE variance over baseline methods, significantly enabling high-quality, real-time wireless VR services.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Learning & Optimization for CV
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Wireless connectivity promises to unshackle virtual reality (VR) experiences, allowing users to engage from anywhere, anytime. However, delivering seamless, high-quality, real-time VR video wirelessly is challenging due to the stringent quality of experience requirements, low latency constraints, and limited VR device capabilities. This paper addresses these challenges by introducing a novel decentralized multi task fair federated learning (DMTFL) based caching that caches and prefetches each VR user's field of view (FOV) at base stations (BSs) based on the caching strategies tailored to each BS. In federated learning (FL) in its naive form, often biases toward certain users, and a single global model fails to capture the statistical heterogeneity across users and BSs. In contrast, the proposed DMTFL algorithm personalizes content delivery by learning individual caching models at each BS. These models are further optimized to perform well under any target distribution, while providing theoretical guarantees via Rademacher complexity and a probably approximately correct (PAC) bound on the loss. Using a realistic VR head-tracking dataset, our simulations demonstrate the superiority of our proposed DMTFL algorithm compared to baseline algorithms.

Problem

• Enhances VR video streaming via decentralized caching
• Addresses fairness and bias in federated learning models
• Personalizes content delivery under statistical heterogeneity

Innovation

• Decentralized multi-task federated learning for caching
• Personalized caching models per base station
• Theoretical guarantees via Rademacher complexity and PAC bound